| one publication added to basket [289349] | Analyzing changes in sediment meiofauna communities using the image analysis software ZooImage
Lindgren, J.F.; Hassellöv, I.-M.; Dahllöf, I. (2013). Analyzing changes in sediment meiofauna communities using the image analysis software ZooImage. J. Exp. Mar. Biol. Ecol. 440: 74-80. https://dx.doi.org/10.1016/j.jembe.2012.12.001
In: Journal of Experimental Marine Biology and Ecology. Elsevier: New York. ISSN 0022-0981; e-ISSN 1879-1697, more
|  |
| Keywords |
Environmental Managers & Monitoring
Fisheries > Gear/Technology
Industry
Marine Sciences
Marine Sciences > Marine Sciences General
Others
Scientific Community
Scientific Publication
Software/Modelling Tool
Marine/Coastal |
| Author keywords |
Community response; Image analysis; Meiofauna; Sediment; ZooImage |
| Project | Top | Authors |
- Association of European marine biological laboratories, more
|
| Authors | | Top |
- Lindgren, J.F.
- Hassellöv, I.-M.
- Dahllöf, I.
|
|
|
| Abstract |
We here propose a novel method of automatic classification of higher taxa from benthic meiofaunal communities using the image analysis software ZooImage. Meiofauna was extracted from sediment at five sites at different depths in the Gullmar Fjord on the Swedish west-coast, and digitalized through scanning. The resulting images were analyzed with the image analysis software, by comparing them to a reference image library of meiofaunal groups of higher taxa, as well as non-faunal groups consisting of different types of debris. The accuracy of the analyses was tested using ZooImage internal cross-validation method, and by comparing digitalized samples from the different sites with manually classified samples. The internal validation accuracy (82-93%) was comparable to prior published studies on zooplankton. The largest errors in classification were within the non-faunal groups and accuracy for classification of faunal groups was as high as 93%. Misclassification within the faunal groups was mainly due to either too few images of some classes in the training set, or to when fauna could not be sufficiently separated from debris in the images used for the library, causing interference in the learning algorithm. Comparison with manual classification confirmed the errors revealed in the internal cross-validation. Statistical analysis revealed differences in the meiofauna communities between different depths as well as a temporal change. |
|
